Even a lucky plushie couldn't save that trade. Down 70K, but the Grand Final is still coming on November 14. Who’s making the comeback? Trade on Phantom. Use code PHANTOM for 10% off. @solana @phantom #phantom# #solana# #frontiertraders# #trading# #crypto# NFA · DYOR

Every Super Heavy booster catch, from the first one to the third. Flight 5 on Oct 13, 2024 was the first time a Super Heavy booster was caught by the tower chopsticks. Flight 7 on Jan 16, 2025 and Flight 8 on March 6, 2025 did it again. Flight 15 is next: the first attempt to catch both the booster and the ship. Targeting Friday, Nov 13, pending FAA approval. Video: @SpaceX

Ever had a great idea turn into your worst loss? Usually it wasn't the idea. It was the size. Set your MIN and MAX before the trade, by asset class. Equities run 2% to 6% per position. Fixed Income 3% to 10%. Commodities 1% to 4%. Longs always larger than shorts. Then scale inside those lines in 50-150bps increments. Never a full position in one move. Full cheat sheet below. Learn the rest of the process at

Every Starship launch, from Flight 1 to the first orbital flight. Flight 1 lifted off on April 20, 2023. Flight 14 lifted off on Sept 28, 2026, reached orbit for the first time and deployed 26 Starlink V3 satellites. Flight 15 is next. Video: @SpaceX

Even with automated evals, only a person can tell why an agent failed. LangChain argues expert judgment is a strategic advantage 🧑‍⚖️ Why human insight is a strategic advantage for building better agents Automated evaluation can flag problems, but it can't explain the cause or the fix. The article lays out three principles for building human review into the evaluation system. 🎯 Principle 1: humans define what "good" looks like Reviewers supply context a trace doesn't contain, such as the standard of quality for the job and what the user was after. Scores with reasoning also expose gaps in the evaluators themselves. 🧵 Principle 2: context makes the judgment hold up Looking at one step misses contradictions with something said several turns earlier. For multi-turn agents, the whole conversation (a thread) is the unit of review. 🔁 Principle 3: turn judgment into evaluation data Labels become ground truth, used to align LLM judges with human scores, update online evaluators, and build golden datasets. In the case study, Fetch Rewards manually checks even product-card images and offer availability. Automation handles scale; the advantage comes from turning expert judgment into a reusable asset. #AIAgents# #LLMEvaluation#